For now 400 GigE is barely in its deployment phase, and its use will be confined to hyperscale data centers at first. But we have all seen how the fastest data rates make their way downward. It is not that many years since 10 Gbps was considered “bleeding edge.” Today some laptops have 40 Gbps (Thunderbolt) interfaces. So it may not be many years before the industry must contend with the cabling infrastructure opportunities that 400 Gbps will bring in its wake.
Cabling opportunities change at a slower pace than data rates. When data center managers install a new cabling infrastructure, they want assurance that it will survive several generations of networking protocols. Data centers are reluctant to abandon old cabling technologies. Even though the death of copper has been proclaimed in the data center since the 1990s it hasn’t come close to happening yet What has happened is that copper cabling has improved its packaging – CAT 7 is something a lot more than the old “telephone wire” – and its price has increased. But copper has endured so far.
With 400 GigE this will change, creating new opportunities for fiber optics in markets where high-end copper cabling has continued to do well despite predictions to the contrary. In a sense, 400 GigE will be the end game of a process that began more than decade ago. Back then copper cabling for InfiniBand had reached a point where they it was too thick and heavy to be used and it was gradually replaced in many instances by active optical cabling.
CIR’s sense of the market is that as 400 GigE spreads copper will get pushed out of high-end networking for much the same reason. Fiber will then become ubiquitous in the data center. But which fiber? As we indicate below, we think that both the OM4 and single-mode markets will get a shot in the arm from the rise of 400 GigE.
Opportunity #1: 400 GigE Extends the Opportunity for OM4
OM3 multimode cables have been in use quite some time, but the newer OM4 cables are common in data centers as well. And at this point CIR believes that data center managers in larger centers are all evaluating their roadmap towards OM4 cabling. The issues that they must consider are reach: OM3 cables may serve as an infrastructure for 400GigE to some extent, but they provide less distance than OM4 cables. Data centers must also consider that OM3 was originally designed with 10GigE in mind.
OM4 cabling provides physical layer with less signal loss and wider bandwidth. This is a crucial advantage in the 400 Gbps and is the enabling factor for the extra distance provided by the OM4 compared to OM3. Also of advantage is the fact that OM4 is completely backward compatible with the OM3 standard and thus is able to serve old transceivers while opening up new opportunities (such as the ability for a comprehensive installation of 400 Gbps) for growth and potentially flexibility as well for the infrastructure.
While the data center will transition to OM4 over time almost no matter what, at CIR we believe that 400 GigE presents a special opportunity for OM4, because it was designed for 4 x 100 GigE in mind, while OM3 is a child of the OM3 era. Once 400 GigE starts to spread, there will be an inflection point in the OM4 revenue curve and migration towards OM4 cabling will start to accelerate.
Opportunity #2 400 GigE’s Impact on SMF
Today, 400 GigE is seen mostly as a tool for connecting routers to large server clusters or switches to routers, but we think 400 GigE will also be used for campus networks that will connect up distributed data centers or connect data centers to disaster recovery locations. CIR believes that this kind of application will require single-mode fiber and SMF is built extensively into the 400 GigE standards.
SMF for datacom remains something of a niche business at present. It doesn’t seem to us that 400 GigE will be enough to push SMF into the mainstream. But it will be yet another factor that will help SMF gain market share of the data center infrastructure in the next few years.
A Threat: 400 GigE and the Death of Copper
While we acknowledge that copper has had a remarkable ability to survive data rate increases. It seems to us with 400 GigE, copper’s luck has run out – there seems no reason that copper will ever make much of a mark on 400 GigE.
CIR believes that this is quite a big deal. Each recent generation of Ethernet has started out with claims that optics will dominate. But somehow, after a year or so, copper has come roaring back again. It is hard to see how this happens with 400 GigE, however. And as 400 GigE get’s deployed, manufacturers of high-end copper cabling for data centers may have to start looking for new markets.